Syndicate content

Information and Communication Technologies

Demystifying machine learning for disaster risk management

Giuseppe Molinario's picture
Also available in: العربية | Español | Français

To some, artificial intelligence is a mysterious term that sparks thoughts of robots and supercomputers. But the truth is machine learning algorithms and their applications, while potentially mathematically complex, are relatively simple to understand. Disaster risk management (DRM) and resilience professionals are, in fact, increasingly using machine learning algorithms to collect better data about risk and vulnerability, make more informed decisions, and, ultimately, save lives.

Artificial intelligence (AI) and machine learning (ML) are used synonymously, but there are broader implications to artificial intelligence than to machine learning. Artificial (General) Intelligence evokes images of Terminator-like dystopian futures, but in reality, what we have now and will have for a long time is simply computers learning from data in autonomous or semi-autonomous ways, in a process known as machine learning.

The Global Facility for Disaster Reduction and Recovery (GFDRR)’s Machine Learning for Disaster Risk Management Guidance Note clarifies and demystifies the confusion around concepts of machine learning and artificial intelligence. Some specific case-studies showing the applications of ML for DRM are illustrated and emphasized. The Guidance Note is useful across the board to a variety of stakeholders, ranging from disaster risk management practitioners in the field to risk data specialists to anyone else curious about this field of computer science.

Machine learning in the field

In one case study, drone and street-level imagery were fed to machine learning algorithms to automatically detect “soft-story” buildings or those most likely to collapse in an earthquake. The project was developed by the World Bank’s Geospatial Operations Support Team (GOST) in Guatemala City, and is just one of many applications where large amounts of data, processed with machine learning, can have very tangible and consequential impacts on saving lives and property in disasters.

The map above illustrates the “Rapid Housing Quality Assessment”, in which the agreement between ML-identified soft-story buildings, and those identified by experts is shown (Sarah Antos/GOST).

Like manna from heaven? The sustainability of Open Source projects

Michael M. Lokshin's picture

Sustainability of OSS is an important, but often overlooked issue. The private sector is struggling to find the right model to maintain and sustain OSS. The International Development Agencies need viable long-term strategies to sustain the OSS projects they are developing, funding, or using.

Two young colleagues invited me for coffee to discuss their proposal to develop an open source software (OSS) system for administering government programs in developing countries. The idea of replacing costly, custom-built proprietary systems with open-source solutions tailored for specific country requirements was very appealing.

“Why pay millions of dollars for a proprietary solution when an open source system will be free?” exclaimed one of the colleagues.

I inquired cautiously, “Have you considered how to maintain these systems once they are deployed? Who will pay for customization and on-going support to the country clients? How do you consistently ensure the quality of the code?”

“The international OSS community will volunteer their time to maintain and improve these systems.” was the reply.

Introducing the online guide to the World Development Indicators: A new way to discover data on development

World Bank Data Team's picture
Also available in: العربية | Español | 中文 | Français

The World Development Indicators (WDI) is the World Bank’s premier compilation of international statistics on global development. Drawing from officially recognized sources and including national, regional, and global estimates, the WDI provides access to almost 1,600 indicators for 217 economies, with some time series extending back more than 50 years. The database helps users—analysts, policymakers, academics, and all those curious about the state of the world—to find information related to all aspects of development, both current and historical.

An annual World Development Indicators report was available in print or PDF format until last year. This year, we introduce the World Development Indicators website: a new discovery tool and storytelling platform for our data which takes users behind the scenes with information about data coverage, curation, and methodologies. The goal is to provide a useful, easily accessible guide to the database and make it easy for users to discover what type of indicators are available, how they’re collected, and how they can be visualized to analyze development trends.

So, what can you do on the new World Development Indicators website?

1. Explore available indicators by theme

The indicators in the WDI are organized according to six thematic areas: Poverty and Inequality, People, Environment, Economy, States and Markets, and Global Links. Each thematic page provides an overview of the type of data available, a list of featured indicators, and information about widely used methodologies and current data challenges.

Applications open for third round of funding for collaborative data innovation projects

World Bank Data Team's picture
Photo Credit: The Crowd and The Cloud


The Global Partnership for Sustainable Development Data and the World Bank Development Data Group are pleased to announce that applications are now open for a third round of support for innovative collaborations for data production, dissemination, and use. This follows two previous rounds of funding awarded in 2017 and earlier in 2018.

This initiative is supported by the World Bank’s Trust Fund for Statistical Capacity Building (TFSCB) with financing from the United Kingdom’s Department for International Development (DFID), the Government of Korea and the Department of Foreign Affairs and Trade of Ireland.

Scaling local data and synergies with official statistics

The themes for this year’s call for proposals are scaling local data for impact, which aims to target innovations that have an established proof of concept which benefits local decision-making, and fostering synergies between the communities of non-official data and official statistics, which looks for collaborations that take advantage of the relative strengths and responsibilities of official (i.e. governmental) and non-official (e.g.,private sector, civil society, social enterprises and academia) actors in the data ecosystem.

Beyond Proof of Concept: do we have the right structure to take disruptive technologies to production?

Michael M. Lokshin's picture
Figure 1: Azure Cognitive Services Algorithm compliments authors’
youthful appearances

“Every company is a technology company”. This idea, popularized by Gartner, can be seen unfolding in every sector of the economy as firms and governments adopt increasingly sophisticated technologies to achieve their goals. The development sector is no exception, and like others, we’re learning a lot about what it takes to apply new technologies to our work at scale.

Last week we published a blog about our experience in using Machine Learning (ML) to reduce the cost of survey data collection. This exercise highlighted some challenges that teams working on innovative projects might face in bringing their innovative ideas to useful implementations. In this post, we argue that:

  1. Disruptive technologies can make things look easy. The cost of experimentation, especially in the software domain, is often low. But quickly developed prototypes belie the complexity of creating robust systems that work at scale. There’s a lot more investment needed to get a prototype into production that you’d think.

  2. Organizations should monitor and invest in many proofs of concept because they can relatively inexpensively learn about their potential, quickly kill the ones that aren’t going anywhere, and identify the narrower pool of promising approaches to continue monitoring and investing resources in.

  3. But organizations should also recognize that the skills needed to make a proof of concept are very different to the skills needed to scale an idea to production. Without a structure or environment to support promising initiatives, even the best projects will die. And without an appetite for long-term investment, applications of disruptive technologies in international development will not reach any meaningful level of scale or usefulness.

The 2018 Atlas of Sustainable Development Goals: an all-new visual guide to data and development

World Bank Data Team's picture
Also available in: Español | العربية | Français
Download PDF (30Mb) / View Online

“The World Bank is one of the world’s largest producers of development data and research. But our responsibility does not stop with making these global public goods available; we need to make them understandable to a general audience.

When both the public and policy makers share an evidence-based view of the world, real advances in social and economic development, such as achieving the Sustainable Development Goals (SDGs), become possible.” - Shanta Devarajan

We’re pleased to release the 2018 Atlas of Sustainable Development Goals. With over 180 maps and charts, the new publication shows the progress societies are making towards the 17 SDGs.

It’s filled with annotated data visualizations, which can be reproducibly built from source code and data. You can view the SDG Atlas online, download the PDF publication (30Mb), and access the data and source code behind the figures.

This Atlas would not be possible without the efforts of statisticians and data scientists working in national and international agencies around the world. It is produced in collaboration with the professionals across the World Bank’s data and research groups, and our sectoral global practices.
 

Trends and analysis for the 17 SDGs

5 Reasons to Check out the World Bank’s new Data Catalog

Malarvizhi Veerappan's picture
Also available in: العربية | Français | Español

Please help us out by completing this short user survey on the new data catalog.

Data is the key ingredient for evidence based policy making. A growing family of artificial intelligence techniques are transforming how we use data for development. But for these and more traditional techniques to be successful, they need a foundation in good data. We need high quality data that is well managed, and that is appropriately stored, accessed, shared and reused.

The World Bank’s new data catalog transforms the way we manage data. It provides access to over 3,000 datasets and 14,000 indicators and includes microdata, time series statistics, and geospatial data.

Open data is at the heart of our strategy

Since its launch in 2010, the World Bank’s Open Data Initiative has provided free, open access to the Bank’s development data. We’ve continuously updated our data dissemination and visualization tools, and we’ve supported countries to launch their own open data initiatives.

We’re strong advocates for open data, but we also recognize that some data, often by virtue of how it has been acquired or the subjects it covers, may have limitations on how it can be used. In the new data catalog, rather than having such data remain unpublished, we’re making many of these previously unpublished datasets available, and we document any restrictions on how they can be used. This new catalog is an extension of the open data catalog and relies heavily on the work previously done by the microdata library.

Your Cow, Plant, Fridge and Elevator Can Talk to You (But Your Kids Still Won’t!)

Raka Banerjee's picture
Download the Report

The Internet of Things (IoT) heralds a new world in which everything (well, almost everything) can now talk to you, through a combination of sensors and analytics. Cows can tell you when they’d like to be milked or when they’re sick, plants can tell you about their soil conditions and light frequency, your fridge can tell you when your food is going bad (and order you a new carton of milk), and your elevator can tell you how well it’s functioning.

At the World Bank, we’re looking at all these things (Things?) from a development angle. That’s the basis behind the new report, “Internet of Things: The New Government to Business Platform”, which focuses on how the Internet of Things can help governments deliver services better. The report looks at the ways that some cities have begun using IoT, and considers how governments can harness its benefits while minimizing potential risks and problems.

In short, it’s still the Wild West in terms of IoT and governments. The report found lots of IoT-related initiatives (lamppost sensors for measuring pollution, real-time transit updates through GPS devices, sensors for measuring volumes in garbage bins), but almost no scaled applications. Part of the story has to do with data – governments are still struggling how to collect and manage the vast quantities of data associated with IoT, and issues of data access and valuation also pose problems.

Five years of investments in open data

Tim Herzog's picture
Also available in: 中文
 
Download the PDF

This year marks the fifth anniversary of the World Bank’s efforts to help countries launch their own open data initiatives, and harness the power of open data to benefit their citizens. A new report provides insights into how open data is benefitting countries, what strategies are working well, what could be improved.

The report provides the most comprehensive snapshot of Bank-funded open data activities to date. In the last five years, the Bank has provided technical assistance and funding for open data activities in over 50 countries, conservatively estimated at more than $50 million from a variety of sources. In many cases Bank funding has leveraged support from other partners or co-sponsorship by countries and other institutions. Within the Bank, the Trust Fund for Statistical Capacity Building (TFSCB) has been the most significant source of funding for open data. The TFSCB has financed over 20 projects in 16 countries, as well as 6 grants for regional and global activities.

Supporting over 45 countries with national and sector-specific open data

Support for open data has taken a variety of forms. To date, 45 Open Data Readiness Assessments (ODRAs) have been completed at national and sub-national levels, which have helped raise awareness and catalyze public and private efforts to advance open data within countries. There are now sector-specific ODRA tools for business, energy, and transport. The Bank has invested in a range of open data learning and knowledge products, including data literacy courses and the Open Data Toolkit, and collaborated with its global partners to support academic research, a series of regional conferences, and open data implementation. The report also found that these initial efforts have catalyzed longer-term project investments, i.e., IBRD loans and IDA credits, with open data implementation components in at least 14 countries.

Hoping for a cloudy future for Caribbean statistics

Michael M. Lokshin's picture
Photo Credit: Lou Gold

Hurricanes Irma and Maria recently devastated the Caribbean region. Infrastructure in Dominica was severely damaged and the country suffered a total loss of its annual agricultural production. The entire population of Barbuda had to be evacuated to Antigua and other islands. Estimates by the World Bank indicate that Irma caused damages equivalent to 14 percent of GDP for Antigua and Barbuda, and up to 200 percent of GDP for Dominica. The increasing frequency of hurricanes poses a threat to the economic development and wellbeing of 40 million people living in the region.

The World Bank and other development institutions acted quickly by offering support to assess damages and losses, respond to the disaster, and assist with recovery by delivering financial packages and supporting emergency operations. However, in the longer term, the focus is on building the resilience of these small island states to natural disasters.

Data: critical for responding to disasters, but also vulnerable to them

Systems of national statistics can provide critical information about the extent of a disaster, help guide recovery operations, and assess the preparedness of countries to future shocks.  At the same time, the reliance of National Statistical Offices (NSOs) on local IT infrastructure makes them highly vulnerable to natural disasters. Computers, servers, and networks cannot operate without power; flooding and high humidity destroys hardware and storage media; looting and breaking into abandoned buildings puts sensitive information at the risk of falling into the wrong hands. Fortifying NSO buildings to withstand Category 5 hurricanes and enabling the offices to continue functioning afterwards is prohibitively expensive. Even if such structures were built, staffing would remain an issue, particularly if the entire population of the country was evacuated (as in case of Barbuda).

Cloud computing provides a very effective way to resolve that problem at a small fraction of the cost.

Pages